CN116385268A - Remote sensing image enhancement method - Google Patents
Remote sensing image enhancement method Download PDFInfo
- Publication number
- CN116385268A CN116385268A CN202310365917.0A CN202310365917A CN116385268A CN 116385268 A CN116385268 A CN 116385268A CN 202310365917 A CN202310365917 A CN 202310365917A CN 116385268 A CN116385268 A CN 116385268A
- Authority
- CN
- China
- Prior art keywords
- resolution image
- pixel
- image
- low
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000012216 screening Methods 0.000 claims abstract description 7
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 230000002708 enhancing effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G06T3/4076—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution using the original low-resolution images to iteratively correct the high-resolution images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a remote sensing image enhancement method, which comprises the following steps: A. synchronously shooting a high-resolution image and a second-resolution image of a remote sensing object; B. comparing the high-resolution image with the low-resolution image, and screening the characteristic region; C. extracting a feature pixel set from a feature region marked in the low resolution image; D. deleting the feature pixel set extracted in the step C from the high-resolution image, and then extracting the rest feature pixel sets; E. and C, carrying out enhancement processing on the feature pixel set extracted in the step C and the step D, replacing a corresponding pixel set in the high-resolution image with the feature pixel set subjected to the enhancement processing, and then carrying out anti-logarithmic transformation on the high-resolution image. The invention can improve the defects of the prior art, simplify the enhancement processing steps and improve the image processing efficiency.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a remote sensing image enhancement method.
Background
Remote sensing monitoring is a common means of detecting near the ground in a large range. After the original remote sensing image is obtained, the remote sensing image needs to be enhanced so as to improve the accuracy of the subsequent remote sensing image analysis. The existing remote sensing image enhancement means are complex in steps, large in operation amount and low in image processing efficiency.
Disclosure of Invention
The invention aims to provide a remote sensing image enhancement method which can solve the defects of the prior art, simplify enhancement processing steps and improve image processing efficiency.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows.
A remote sensing image enhancement method comprising the steps of:
A. synchronously shooting a high-resolution image and a second-resolution image of a remote sensing object;
B. comparing the high-resolution image with the low-resolution image, and screening the characteristic region;
C. extracting a feature pixel set from a feature region marked in the low resolution image;
D. deleting the feature pixel set extracted in the step C from the high-resolution image, and then extracting the rest feature pixel sets;
E. and C, carrying out enhancement processing on the feature pixel set extracted in the step C and the step D, replacing a corresponding pixel set in the high-resolution image with the feature pixel set subjected to the enhancement processing, and then carrying out anti-logarithmic transformation on the high-resolution image.
Preferably, in step B, screening the feature region includes the steps of,
b1, respectively carrying out logarithmic transformation on the high-resolution image and the low-resolution image;
b2, respectively carrying out high-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a high-frequency image, and respectively carrying out low-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a low-frequency image;
and B3, traversing the high-frequency image and the low-frequency image with high resolution, the high-frequency image and the low-frequency image with low resolution respectively, marking the areas with gray scale change ranges smaller than a set threshold value in each image, comparing the marked areas in the four images, deleting the marked areas in the four images in the high-resolution image and the low-resolution image, and taking the rest areas as characteristic areas.
Preferably, in step C, extracting the set of feature pixels in the marked feature region in the low resolution image comprises the steps of,
c1, gradually expanding the identification radius outwards by taking any gray extreme point in the characteristic region as a central dot;
and C2, after the radius is sequentially identified every time expansion, if no characteristic pixel exists in the radius identification range, calculating the deviation of the included angle between the Euler direction of the newly increased pixel point and the center dot in the radius identification range and the gray gradient direction of the newly increased pixel point and the deviation of the gray gradient amplitude of the newly increased pixel point and the gray gradient difference of the newly increased pixel point and the center origin, judging the pixel point as the characteristic pixel if the calculated included angle and the gray gradient deviation are smaller than a set threshold value, and if the characteristic pixel exists in the radius identification range, calculating the included angle between the Euler direction of the newly increased pixel point and the gray gradient direction of the newly increased pixel point in the radius identification range and the gray gradient amplitude of the newly increased pixel point and the gray gradient difference of the newly increased pixel point and the pixel point closest to the Euler distance, and judging the pixel point as the characteristic pixel if the calculated included angle and the gray gradient deviation are smaller than the set threshold value.
Preferably, in step D, extracting the set of feature pixels in the marked feature region in the high resolution image comprises the steps of,
d1, arbitrarily selecting a plurality of pixel points in the characteristic region as starting points;
d2, marking the pixel points adjacent to the starting point along the gray gradient direction of the starting point from the starting point, marking the pixel points adjacent to the starting point along the gray gradient direction of the newly marked pixel points until the pixel points to be marked are marked, ending the secondary marking process, and deleting other pixel points in a closed area surrounded by the marked pixel points;
and D3, repeating the step D2 until all the rest pixel points in the characteristic region are marked, wherein the rest pixel points are characteristic pixels.
Preferably, in step E, the enhancement processing is performed on the feature pixel set using a gamma correction method.
The beneficial effects brought by adopting the technical scheme are as follows: the invention abandons the technical route of directly enhancing the remote sensing image in the prior art, and utilizes the high-low resolution image to firstly perform comparison and extraction of the characteristic pixel set, so that only the extracted characteristic pixel set is enhanced, the image processing effect is ensured, and the overall operation amount is effectively reduced. And the sensitivity of the high-low frequency image to gray level change is utilized, the characteristic region is marked firstly, and the range of extracting the characteristic pixel set is further narrowed. Because the volume of the low-resolution image is smaller and the image precision is not high, a direct calculation mode is adopted to extract the characteristic pixel set; because the volume of the high-resolution image is larger and the image precision is high, the characteristic pixel set is extracted by adopting an iterative elimination mode. Thereby achieving the purpose of improving the image processing efficiency.
Drawings
FIG. 1 is a flow chart of one embodiment of the present invention.
Detailed Description
Referring to fig. 1, one embodiment of the present invention includes the steps of:
A. synchronously shooting a high-resolution image and a second-resolution image of a remote sensing object;
B. comparing the high-resolution image with the low-resolution image, and screening the characteristic region;
screening the feature region includes the steps of,
b1, respectively carrying out logarithmic transformation on the high-resolution image and the low-resolution image;
b2, respectively carrying out high-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a high-frequency image, and respectively carrying out low-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a low-frequency image;
b3, traversing the high-frequency image and the low-frequency image with high resolution, the high-frequency image and the low-frequency image with low resolution respectively, marking the areas with gray scale change ranges smaller than a set threshold value in each image, comparing the marked areas in the four images, deleting the marked areas in the four images in the high-resolution image and the low-resolution image, and taking the rest areas as characteristic areas;
C. extracting a feature pixel set from a feature region marked in the low resolution image; comprises the steps of,
c1, gradually expanding the identification radius outwards by taking any gray extreme point in the characteristic region as a central dot;
c2, after sequentially identifying the radius by expansion, if no characteristic pixel exists in the radius identification range, calculating the deviation of the included angle between the Euler direction of the newly added pixel point and the center dot in the radius identification range and the gray gradient direction of the newly added pixel point and the deviation of the gray gradient amplitude of the newly added pixel point and the gray gradient difference of the newly added pixel point and the center origin, judging the pixel point as a characteristic pixel if the calculated included angle and gray gradient deviation are smaller than a set threshold value, and if the characteristic pixel exists in the radius identification range, calculating the deviation of the included angle between the Euler direction of the newly added pixel point and the gray gradient direction of the newly added pixel point in the radius identification range and the gray gradient amplitude of the newly added pixel point and the gray gradient difference of the newly added pixel point and the gray gradient direction of the newly added pixel point, and judging the pixel point as the characteristic pixel if the calculated included angle and gray gradient deviation are smaller than the set threshold value;
D. deleting the feature pixel set extracted in the step C from the high-resolution image, and then extracting the rest feature pixel sets; the method comprises the following steps of,
d1, arbitrarily selecting a plurality of pixel points in the characteristic region as starting points;
d2, marking the pixel points adjacent to the starting point along the gray gradient direction of the starting point from the starting point, marking the pixel points adjacent to the starting point along the gray gradient direction of the newly marked pixel points until the pixel points to be marked are marked, ending the secondary marking process, and deleting other pixel points in a closed area surrounded by the marked pixel points;
d3, repeating the step D2 until all the rest pixel points in the characteristic region are marked, wherein the rest pixel points are characteristic pixels;
E. and C, enhancing the feature pixel set extracted in the step C and the step D by using a gamma correction method, replacing the corresponding pixel set in the high-resolution image by using the feature pixel set after enhancing, and performing anti-logarithmic transformation on the high-resolution image.
In the description of the present invention, it should be understood that the terms "longitudinal," "transverse," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the present invention, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (5)
1. The remote sensing image enhancement method is characterized by comprising the following steps of:
A. synchronously shooting a high-resolution image and a second-resolution image of a remote sensing object;
B. comparing the high-resolution image with the low-resolution image, and screening the characteristic region;
C. extracting a feature pixel set from a feature region marked in the low resolution image;
D. deleting the feature pixel set extracted in the step C from the high-resolution image, and then extracting the rest feature pixel sets;
E. and C, carrying out enhancement processing on the feature pixel set extracted in the step C and the step D, replacing a corresponding pixel set in the high-resolution image with the feature pixel set subjected to the enhancement processing, and then carrying out anti-logarithmic transformation on the high-resolution image.
2. The remote sensing image enhancement method according to claim 1, wherein: in step B, screening the feature region includes the steps of,
b1, respectively carrying out logarithmic transformation on the high-resolution image and the low-resolution image;
b2, respectively carrying out high-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a high-frequency image, and respectively carrying out low-pass filtering on the transformed high-resolution image and the transformed low-resolution image to obtain a low-frequency image;
and B3, traversing the high-frequency image and the low-frequency image with high resolution, the high-frequency image and the low-frequency image with low resolution respectively, marking the areas with gray scale change ranges smaller than a set threshold value in each image, comparing the marked areas in the four images, deleting the marked areas in the four images in the high-resolution image and the low-resolution image, and taking the rest areas as characteristic areas.
3. The remote sensing image enhancement method according to claim 2, wherein: in step C, extracting a set of feature pixels in a feature region marked in the low resolution image comprises the steps of,
c1, gradually expanding the identification radius outwards by taking any gray extreme point in the characteristic region as a central dot;
and C2, after the radius is sequentially identified every time expansion, if no characteristic pixel exists in the radius identification range, calculating the deviation of the included angle between the Euler direction of the newly increased pixel point and the center dot in the radius identification range and the gray gradient direction of the newly increased pixel point and the deviation of the gray gradient amplitude of the newly increased pixel point and the gray gradient difference of the newly increased pixel point and the center origin, judging the pixel point as the characteristic pixel if the calculated included angle and the gray gradient deviation are smaller than a set threshold value, and if the characteristic pixel exists in the radius identification range, calculating the included angle between the Euler direction of the newly increased pixel point and the gray gradient direction of the newly increased pixel point in the radius identification range and the gray gradient amplitude of the newly increased pixel point and the gray gradient difference of the newly increased pixel point and the pixel point closest to the Euler distance, and judging the pixel point as the characteristic pixel if the calculated included angle and the gray gradient deviation are smaller than the set threshold value.
4. The remote sensing image enhancement method according to claim 2, wherein: in step D, extracting a set of feature pixels in a feature region marked in the high resolution image comprises the steps of,
d1, arbitrarily selecting a plurality of pixel points in the characteristic region as starting points;
d2, marking the pixel points adjacent to the starting point along the gray gradient direction of the starting point from the starting point, marking the pixel points adjacent to the starting point along the gray gradient direction of the newly marked pixel points until the pixel points to be marked are marked, ending the secondary marking process, and deleting other pixel points in a closed area surrounded by the marked pixel points;
and D3, repeating the step D2 until all the rest pixel points in the characteristic region are marked, wherein the rest pixel points are characteristic pixels.
5. The remote sensing image enhancement method according to claim 1, wherein: in step E, enhancement processing is performed on the feature pixel set by using a gamma correction method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310365917.0A CN116385268A (en) | 2023-04-06 | 2023-04-06 | Remote sensing image enhancement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310365917.0A CN116385268A (en) | 2023-04-06 | 2023-04-06 | Remote sensing image enhancement method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116385268A true CN116385268A (en) | 2023-07-04 |
Family
ID=86974732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310365917.0A Pending CN116385268A (en) | 2023-04-06 | 2023-04-06 | Remote sensing image enhancement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385268A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611977A (en) * | 2024-01-23 | 2024-02-27 | 深圳智锐通科技有限公司 | Signal processing circuit in visual recognition system |
-
2023
- 2023-04-06 CN CN202310365917.0A patent/CN116385268A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117611977A (en) * | 2024-01-23 | 2024-02-27 | 深圳智锐通科技有限公司 | Signal processing circuit in visual recognition system |
| CN117611977B (en) * | 2024-01-23 | 2024-04-30 | 深圳智锐通科技有限公司 | Signal processing circuit in visual recognition system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107154040B (en) | Tunnel lining surface image crack detection method | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| CN108364280B (en) | Method and equipment for automatically describing structural crack and accurately measuring width | |
| CN110084241B (en) | Automatic ammeter reading method based on image recognition | |
| CN109785285B (en) | Insulator damage detection method based on ellipse characteristic fitting | |
| CN112419250A (en) | Pavement crack digital image extraction, crack repair and crack parameter calculation method | |
| CN107038416B (en) | Pedestrian detection method based on binary image improved HOG characteristics | |
| CN113344956B (en) | Ground feature contour extraction and classification method based on unmanned aerial vehicle aerial photography three-dimensional modeling | |
| CN109559324A (en) | A kind of objective contour detection method in linear array images | |
| CN110533679B (en) | SAR image edge detection method based on logarithm transformation and gabor convolution | |
| CN114219773B (en) | Pre-screening and calibrating method for bridge crack detection data set | |
| CN110245600B (en) | Unmanned aerial vehicle road detection method for self-adaptive initial quick stroke width | |
| CN116385268A (en) | Remote sensing image enhancement method | |
| CN114596551A (en) | Vehicle-mounted forward-looking image crack detection method | |
| CN112307803A (en) | Digital geological outcrop crack extraction method and device | |
| CN113177456A (en) | Remote sensing target detection method based on single-stage full convolution network and multi-feature fusion | |
| CN101739667B (en) | Non-downsampling contourlet transformation-based method for enhancing remote sensing image road | |
| CN110555373A (en) | Concrete vibration quality real-time detection method based on image recognition | |
| CN113610024B (en) | Multi-strategy deep learning remote sensing image small target detection method | |
| CN117036737A (en) | Feature extraction and matching method based on information entropy, GMS and LC significant detection | |
| CN117274240A (en) | Bearing platform foundation concrete surface crack identification method | |
| CN111091071A (en) | Underground target detection method and system based on ground penetrating radar hyperbolic wave fitting | |
| CN117152163B (en) | Bridge construction quality visual detection method | |
| CN117710399A (en) | Crack contour extraction method in geological survey based on vision | |
| CN116718599A (en) | Apparent crack length measurement method based on three-dimensional point cloud data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |